dharma-retro

Extracts wins, misses, root causes, and next actions from completed work.

Updated Aug 5, 2026
One-click install
npx skills add https://github.com/AmitabhainArunachala/dharma_swarmv.01 --skill dharma-retro-amitabhainarunachala
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dharma-retro
Source: https://github.com/AmitabhainArunachala/dharma_swarmv.01/tree/main/mode_pack/claude/retro
Command: npx skills add https://github.com/AmitabhainArunachala/dharma_swarmv.01 --skill dharma-retro-amitabhainarunachala

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After finishing a project, release, or incident, teams often move on without capturing what actually happened, losing valuable lessons and repeating the same mistakes. This Skill structures the retrospective process so real learning and concrete follow-up actions are produced instead of vague impressions. ## Core Features & Use Cases - Structured Retrospective Output: Produces four required sections: wins, misses, root causes, and next actions. - Blame-Free Analysis Rules: Enforces no blame theater, no empty praise, and a preference for system learning over personal mythology. - Downstream Handoff: Feeds retrospective findings into review and incident workflows such as engineering reviews, CEO reviews, or incident command processes. - Use Case: After shipping a release that included a production incident, run this mode to document what worked, what failed, why it failed, and which concrete actions should improve the system before the next cycle. ## Quick Start Run a retrospective on the release we just completed and produce the wins, misses, root causes, and next actions.

Frequently Asked Questions about dharma-retro

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a retrospective after a project or release?▼

Invoke this mode after a meaningful piece of work, release, or incident. It guides the analysis and produces four required sections: wins, misses, root causes, and next actions that improve the system.

What should a good retrospective output include?▼

A good retrospective output includes what worked, what failed, the root causes behind failures, and concrete next actions. This Skill enforces exactly that four-part structure for every session.

Can this be used for incident postmortems?▼

Yes, the mode explicitly covers incidents alongside releases and general work. Its findings can be handed off to an incident commander workflow for follow-up and prevention.

How does it avoid blame in team retrospectives?▼

The Skill enforces explicit rules: no blame theater, no empty praise, and a preference for system learning over personal mythology. This keeps the analysis focused on process and system causes rather than individuals.

When should I not use a structured retrospective?▼

Skip it for trivial tasks with no meaningful learning potential. The mode is designed for meaningful work, releases, or incidents where root cause analysis and follow-up actions justify the effort.